专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20140049549A1 EFFICIENT PLACEMENT OF TEXTURE BARRIER INSTRUCTIONS 有权
标题翻译：高效布置纹理障碍指示
公开(公告)号：US20140049549A1
公开(公告)日：2014-02-20
申请号：US13590075
申请日：2012-08-20
申请人： Maxim Lukyanov , Boris Beylin , Robert Steven Glanville , Alexander Grosul
发明人： Maxim Lukyanov , Boris Beylin , Robert Steven Glanville , Alexander Grosul
IPC分类号： G06T1/00
CPC分类号： G06T1/60
摘要： One embodiment of the present invention sets forth a technique for placing texture barrier instructions within a thread program to advantageously enable efficient and correct operation of the thread program. A thread program compiler statically determines a pending request count needed to progress beyond a particular texture barrier instruction, which blocks execution of subsequent instructions that depend on previously requested data. Each instance of the thread program blocks execution at the barrier instruction until a pending request count condition is satisfied. This technique may advantageously reduce power consumption in a graphics processing unit by eliminating power consumption associated with conventional, generalized scoreboard resources.
摘要翻译：本发明的一个实施例提出了一种用于将纹理屏障指令放置在线程程序内以有利地实现线程序的有效和正确操作的技术。线程程序编译器静态地确定超出特定纹理屏障指令所需的待处理请求计数，该指令阻止依赖先前请求的数据的后续指令的执行。线程程序的每个实例阻止在障碍指令执行，直到满足待处理的请求计数条件。该技术可以有利地通过消除与传统的广义记分板资源相关联的功耗来降低图形处理单元中的功耗。

2. 发明授权

US08843913B2 Dynamic linking and loading of post-processing kernels 有权
标题翻译：后处理内核的动态链接和加载
公开(公告)号：US08843913B2
公开(公告)日：2014-09-23
申请号：US11758437
申请日：2007-06-05
申请人： Guei-Yuan Lueh , Xiaoying He , Xuefeng Zhang , Yuenian Yang , Ping Liu , Hong Jiang , Maxim Lukyanov
发明人： Guei-Yuan Lueh , Xiaoying He , Xuefeng Zhang , Yuenian Yang , Ping Liu , Hong Jiang , Maxim Lukyanov
IPC分类号： G06F9/44 , G06F9/445 , G06F9/45
CPC分类号： G06F9/44521 , G06F8/41 , G06F9/4411
摘要： A computer system may generate a plurality of component kernels, which are to be linked during the runtime. The system may determine whether a combined kernel K is present in response to receiving a first request to retrieve the combined kernel K. The system may compose the combined kernel K from the selected component kernels of the plurality of component kernels during the runtime if the combined kernel is not already present.
摘要翻译：计算机系统可以生成将在运行时链接的多个组件内核。系统可以确定是否存在组合的内核K以响应于接收到检索组合的内核K的第一请求。如果组合的系统可以在运行时期期间从多个组件内核的选定的组件内核中组合组合的内核K 内核不存在。

3. 发明申请

US20080307404A1 DYNAMIC LINKING AND LOADING OF POST-PROCESSING KERNELS 有权
标题翻译：动态连接和加载后处理器的动态
公开(公告)号：US20080307404A1
公开(公告)日：2008-12-11
申请号：US11758437
申请日：2007-06-05
申请人： Guei Yuan Lueh , Xiaoying He , Xuefeng Zhang , Nick Y. Yang , Ping Liu , Jiang H. Hong , Maxim Lukyanov
发明人： Guei Yuan Lueh , Xiaoying He , Xuefeng Zhang , Nick Y. Yang , Ping Liu , Jiang H. Hong , Maxim Lukyanov
IPC分类号： G06F9/44
CPC分类号： G06F9/44521 , G06F8/41 , G06F9/4411
摘要： A computer system may generate a plurality of component kernels, which are to be linked during the runtime. The system may determine whether a combined kernel K is present in response to receiving a first request to retrieve the combined kernel K. The system may compose the combined kernel K from the selected component kernels of the plurality of component kernels during the runtime if the combined kernel is not already present.
摘要翻译：计算机系统可以生成将在运行时链接的多个组件内核。系统可以确定是否存在组合的内核K以响应于接收到检索组合的内核K的第一请求。如果组合的系统可以在运行时期期间从多个组件内核的选定的组件内核中组合组合的内核K 内核不存在。

4. 发明授权

US09142005B2 Efficient placement of texture barrier instructions 有权
标题翻译：高效放置纹理屏障指令
公开(公告)号：US09142005B2
公开(公告)日：2015-09-22
申请号：US13590075
申请日：2012-08-20
申请人： Maxim Lukyanov , Boris Beylin , Robert Steven Glanville , Alexander Grosul
发明人： Maxim Lukyanov , Boris Beylin , Robert Steven Glanville , Alexander Grosul
IPC分类号： G06T1/00 , G06T1/60
CPC分类号： G06T1/60
摘要： One embodiment of the present invention sets forth a technique for placing texture barrier instructions within a thread program to advantageously enable efficient and correct operation of the thread program. A thread program compiler statically determines a pending request count needed to progress beyond a particular texture barrier instruction, which blocks execution of subsequent instructions that depend on previously requested data. Each instance of the thread program blocks execution at the barrier instruction until a pending request count condition is satisfied. This technique may advantageously reduce power consumption in a graphics processing unit by eliminating power consumption associated with conventional, generalized scoreboard resources.
摘要翻译：本发明的一个实施例提出了一种用于将纹理屏障指令放置在线程程序内以有利地实现线程序的有效和正确操作的技术。线程程序编译器静态地确定超出特定纹理屏障指令所需的待处理请求计数，该指令阻止依赖先前请求的数据的后续指令的执行。线程程序的每个实例阻止在障碍指令执行，直到满足待处理的请求计数条件。该技术可以有利地通过消除与传统的广义记分板资源相关联的功耗来降低图形处理单元中的功耗。

5. 发明申请

US20150143387A1 DYNAMIC LINKING AND LOADING OF POST-PROCESSING KERNELS 有权
标题翻译：动态连接和加载后处理器的动态
公开(公告)号：US20150143387A1
公开(公告)日：2015-05-21
申请号：US14476285
申请日：2014-09-03
申请人： Guei Yuan LUEH , Xiaoying HE , Xuefeng ZHANG , Yuenian YANG , Ping LlU , Hong JIANG , Maxim LUKYANOV
发明人： Guei Yuan LUEH , Xiaoying HE , Xuefeng ZHANG , Yuenian YANG , Ping LlU , Hong JIANG , Maxim LUKYANOV
IPC分类号： G06F9/445
CPC分类号： G06F9/44521 , G06F8/41 , G06F9/4411
摘要： A computer system may generate a plurality of component kernels, which are to be linked during the runtime. The system may determine whether a combined kernel K is present in response to receiving a first request to retrieve the combined kernel K. The system may compose the combined kernel K from the selected component kernels of the plurality of component kernels during the runtime if the combined kernel is not already present.
摘要翻译：计算机系统可以生成将在运行时链接的多个组件内核。系统可以确定是否存在组合的内核K以响应于接收到检索组合的内核K的第一请求。如果组合的系统可以在运行时期期间从多个组件内核的选定的组件内核中组合组合的内核K 内核不存在。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式